Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to angels and their states of grace or loss

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Barbar
    -0.16
    fec
    -0.15
    æ»ij
    -0.15
     wur
    -0.15
     Turtle
    -0.14
     MART
    -0.14
    ogn
    -0.14
     radix
    -0.14
     builder
    -0.13
     educated
    -0.13
    POSITIVE LOGITS
     Hollow
    0.31
     shin
    0.29
     Ble
    0.29
     Ich
    0.28
     Shin
    0.27
     Soul
    0.26
     hollow
    0.25
     BLE
    0.25
     bleach
    0.25
     ble
    0.24
    Act Density 0.006%

    No Known Activations